CN112637568A - Distributed security monitoring method and system based on multi-node edge computing equipment - Google Patents
Distributed security monitoring method and system based on multi-node edge computing equipment Download PDFInfo
- Publication number
- CN112637568A CN112637568A CN202011545945.3A CN202011545945A CN112637568A CN 112637568 A CN112637568 A CN 112637568A CN 202011545945 A CN202011545945 A CN 202011545945A CN 112637568 A CN112637568 A CN 112637568A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- image data
- monitoring image
- target
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B7/00—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00
- G08B7/06—Signalling systems according to more than one of groups G08B3/00 - G08B6/00; Personal calling systems according to more than one of groups G08B3/00 - G08B6/00 using electric transmission, e.g. involving audible and visible signalling through the use of sound and light sources
Abstract
The invention provides a distributed safety monitoring method and a system based on multi-node edge computing equipment, which preprocesses and stores monitoring image data generated by monitors arranged in different monitoring areas in a distributed mode, calls appropriate monitoring image data according to the corresponding monitoring area position and/or monitoring time requirement and analyzes and processes the monitoring image data, thereby carrying out safety alarm operation on the corresponding monitoring areas according to whether the image picture abnormity exists in the monitoring image data, thus realizing comprehensive monitoring and efficient safety alarm on the different monitoring areas and ensuring that all monitoring areas can obtain timely and reliable safety monitoring.
Description
Technical Field
The invention relates to the technical field of distributed security monitoring, in particular to a distributed security monitoring method and a distributed security monitoring system based on multi-node edge computing equipment.
Background
The distributed monitoring system obtains corresponding monitoring information by respectively arranging monitors in different monitoring areas, and uploads the monitoring information to a corresponding data center for storage so as to be convenient for subsequently calling the corresponding monitoring information. The distributed monitoring system takes the monitors distributed in different monitoring areas as a computing node, and can greatly improve the monitoring comprehensiveness and the real-time performance of the distributed monitoring system. However, a large amount of monitoring information is usually stored in the data center, and in order to perform accurate security monitoring and alarm on a corresponding monitoring area, the corresponding monitoring information and corresponding analysis processing need to be extracted from the data center, which puts a high requirement on accurately processing the monitoring information in the subsequent process. Therefore, there is a need in the art for a method and a system for performing efficient and accurate analysis and processing on monitoring information generated by a distributed monitoring system to perform timely and fast security monitoring on a corresponding monitoring area.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a distributed security monitoring method and a system based on multi-node edge computing equipment, which are characterized in that monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas are obtained, the monitoring image data are pre-processed, then the monitoring image data are stored, monitoring image data meeting the requirements of preset monitoring area positions and/or preset monitoring time are called from the stored monitoring image data according to a data calling instruction from a cloud terminal, whether the called monitoring image data have abnormal image pictures or not is judged, and a security alarm operation is carried out on the corresponding monitoring areas according to the judged result; therefore, the distributed safety monitoring method and the system based on the multi-node edge computing equipment preprocess and store the monitoring image data generated by the monitors arranged in different monitoring areas in a distributed mode, and call appropriate monitoring image data for analysis and processing according to the corresponding monitoring area position and/or monitoring time requirements, so that the corresponding monitoring areas are subjected to safety alarm operation according to the condition whether image picture abnormity exists in the monitoring image data, thus realizing comprehensive monitoring and efficient safety alarm of the different monitoring areas and ensuring that all monitoring areas can obtain timely and reliable safety monitoring.
The invention provides a distributed security monitoring method based on multi-node edge computing equipment, which is characterized by comprising the following steps of:
step S1, acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas, preprocessing the monitoring image data, and storing the monitoring image data;
step S2, calling monitoring image data meeting the requirement of a preset monitoring area position and/or the requirement of preset monitoring time from the stored monitoring image data according to a data calling instruction from the cloud terminal;
step S3, judging whether the called monitoring image data has abnormal image picture condition, and according to the judgment result, carrying out safety alarm operation to the corresponding monitoring area;
further, in step S1, acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas, preprocessing the monitoring image data, and storing the monitoring image data specifically includes:
step S101, instructing a plurality of monitors to scan and shoot in respective corresponding monitored areas so as to obtain panoramic monitoring image data of the monitored areas;
step S102, extracting a plurality of monitoring image frames from the panoramic monitoring image data according to a preset time interval, wherein the plurality of monitoring image frames cover the monitoring area together, and performing background noise removal processing, graying processing and image edge sharpening processing on the plurality of monitoring image frames so as to obtain a plurality of preprocessed monitoring image frames;
step S103, storing a plurality of preprocessed monitoring image frames to a data center according to a shooting time axis of the monitor;
further, in step S2, according to a data retrieval instruction from a cloud terminal, retrieving, from the stored monitoring image data, monitoring image data that meets a preset monitoring area position requirement and/or a preset monitoring time requirement specifically includes:
step S201, acquiring a data calling instruction from a cloud terminal, and analyzing the data calling instruction so as to determine monitoring area position information and/or monitoring time information which needs to be subjected to data calling;
step S202, according to the position information and/or the monitoring time information of the monitoring area, searching and positioning from the data center to obtain monitoring image data matched with the position information and/or the monitoring time information of the monitoring area;
further, in step S3, determining whether the called monitoring image data has an abnormal image, and performing a security alarm operation on the corresponding monitoring area according to the determination result specifically includes:
step S301, separating the taken monitoring image data to obtain a corresponding background picture and a character picture, and respectively extracting and processing image texture distribution information of the background picture and the character picture to obtain corresponding background picture texture distribution information and character picture texture distribution information;
step S302, according to the background picture texture distribution information and the figure picture texture distribution information, respectively determining a background picture texture change value corresponding to the background picture and a figure picture texture change value corresponding to the figure picture, and determining an absolute value of a difference value between the background picture texture change value and the figure picture texture change value;
step S303, comparing the absolute value of the difference with a preset difference threshold, if the absolute value of the difference is smaller than the preset difference threshold, determining that the called monitoring image data has no image frame abnormity, otherwise, determining that the called monitoring image data has the image frame abnormity;
step S304, carrying out safety alarm operation in a sound mode and/or a light mode on a monitoring area corresponding to the monitoring image data with the determined abnormal image picture;
further, in step S3, determining whether the called monitoring image data has an abnormal image, and performing a security alarm operation on the corresponding monitoring area according to the determination result specifically includes:
calling two target monitoring images within a preset interval duration, dividing each target monitoring image into a target number of regions with equal area size, and obtaining texture features in each region in each target monitoring image;
calculating the color recovery factor of each target monitoring image according to the texture features in each region in each target monitoring image by using the following formula (1),
in the above formula (1), C1A color recovery factor representing the 1 st target monitor image, N representing the number of divided regions, Si1Expressing the definition of textural features in the ith area of the 1 st target monitoring image, beta expressing a gain coefficient, log expressing a logarithm operation, theta expressing a preset external environment influence factor coefficient, Ii1Linear intensity, L, of textural features in the ith region of the 1 st target monitor imagei1Length, L, of the i-th area representing the 1 st target monitoring imagei2Indicating the width of the ith area of the 1 st target monitoring image;
determining the current change degree of the 2 nd target monitoring image relative to the 1 st target monitoring image by using the following formula (2) and the color recovery factor of each target monitoring image,
in the above formula (2), b represents the current degree of change of the 2 nd target monitoring image relative to the 1 st target monitoring image, K represents a contrast factor, C2A color recovery factor representing the 2 nd target monitor image, A representing the number of feature points in the 2 nd target monitor image, Q2jRepresenting the size parameter of the jth characteristic point in the 2 nd target monitoring image, B representing the number of the characteristic points in the 1 st target monitoring image, D1uA size parameter T representing the u-th feature point in the 1 st target monitoring image2Indicates the photographing time length, T, of the 2 nd target monitoring image1The shooting time of the 1 st target monitoring image is represented, and the T represents the interval time between the 1 st target monitoring image and the 2 nd target monitoring image;
and confirming whether the current change degree is within a preset change degree interval, if so, judging that the two target monitoring images have no abnormal image picture condition, otherwise, judging that the two target monitoring images have the abnormal image picture condition, and sending an alarm prompt to a user.
The invention also provides a distributed safety monitoring system based on the multi-node edge computing equipment, which is characterized by comprising a monitoring image data acquisition module, a monitoring image data preprocessing and storing module, a monitoring image data calling module and a monitoring area safety alarm module; wherein the content of the first and second substances,
the monitoring image data acquisition module is used for acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas;
the monitoring image data preprocessing and storing module is used for preprocessing the monitoring image data and then storing the monitoring image data;
the monitoring image data calling module is used for calling monitoring image data meeting the position requirement and/or the preset monitoring time requirement of a preset monitoring area from the stored monitoring image data according to a data calling instruction from a cloud terminal;
the monitoring area safety alarm module is used for judging whether the called monitoring image data has abnormal image pictures or not and carrying out safety alarm operation on the corresponding monitoring area according to the judgment result;
further, the acquiring of the monitoring image data by the monitoring image data acquiring module includes:
instructing a plurality of monitors to carry out scanning shooting in respective corresponding monitored areas so as to obtain panoramic monitoring image data about the monitored areas;
and the number of the first and second groups,
after the monitoring image data preprocessing and storing module preprocesses the monitoring image data, storing the monitoring image data specifically comprises:
extracting a plurality of monitoring image frames from the panoramic monitoring image data according to a preset time interval, wherein the plurality of monitoring image frames cover the monitoring area together, and performing background noise removal processing, graying processing and image edge sharpening processing on the plurality of monitoring image frames so as to obtain a plurality of preprocessed monitoring image frames;
then, storing a plurality of preprocessed monitoring image frames to a data center according to a shooting time axis of the monitor;
further, the monitoring image data calling module calls monitoring image data meeting the preset monitoring area position requirement and/or the preset monitoring time requirement from the stored monitoring image data according to a data calling instruction from a cloud terminal, and the monitoring image data calling module specifically comprises:
acquiring a data calling instruction from a cloud terminal, and analyzing the data calling instruction so as to determine monitoring area position information and/or monitoring time information which needs to be subjected to data calling;
searching and positioning from the data center according to the monitoring area position information and/or the monitoring time information to obtain monitoring image data matched with the monitoring area position information and/or the monitoring time information;
further, the monitoring area security alarm module judges whether the called monitoring image data has the abnormal image picture condition, and according to the judgment result, the security alarm operation for the corresponding monitoring area specifically includes:
separating the called monitoring image data to obtain a corresponding background picture and a character picture, and respectively extracting and processing image texture distribution information of the background picture and the character picture so as to obtain corresponding background picture texture distribution information and character picture texture distribution information;
respectively determining a background picture texture change value corresponding to the background picture and a figure picture texture change value corresponding to the figure picture according to the background picture texture distribution information and the figure picture texture distribution information, and determining an absolute value of a difference value between the background picture texture change value and the figure picture texture change value;
comparing the absolute value of the difference with a preset difference threshold, if the absolute value of the difference is smaller than the preset difference threshold, determining that the condition of image frame abnormality does not exist in the called monitoring image data, otherwise, determining that the condition of image frame abnormality exists in the called monitoring image data;
and carrying out safety alarm operation in a sound mode and/or a light mode on a monitoring area corresponding to the monitoring image data with the determined image picture abnormity.
Compared with the prior art, the distributed security monitoring method and system based on the multi-node edge computing device acquire the monitoring image data generated by the plurality of monitors in the corresponding monitoring areas respectively, preprocess the monitoring image data, store the monitoring image data, call the monitoring image data meeting the position requirement and/or the requirement of the preset monitoring time from the stored monitoring image data according to the data call instruction from the cloud terminal, judge whether the called monitoring image data has the condition of abnormal image pictures, and perform security alarm operation on the corresponding monitoring areas according to the judgment result; therefore, the distributed safety monitoring method and the system based on the multi-node edge computing equipment preprocess and store the monitoring image data generated by the monitors arranged in different monitoring areas in a distributed mode, and call appropriate monitoring image data for analysis and processing according to the corresponding monitoring area position and/or monitoring time requirements, so that the corresponding monitoring areas are subjected to safety alarm operation according to the condition whether image picture abnormity exists in the monitoring image data, thus realizing comprehensive monitoring and efficient safety alarm of the different monitoring areas and ensuring that all monitoring areas can obtain timely and reliable safety monitoring.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a distributed security monitoring method based on a multi-node edge computing device according to the present invention.
Fig. 2 is a schematic structural diagram of a distributed security monitoring system based on a multi-node edge computing device according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flowchart of a distributed security monitoring method based on a multi-node edge computing device according to an embodiment of the present invention. The distributed security monitoring method based on the multi-node edge computing equipment comprises the following steps:
step S1, acquiring the monitoring image data generated by a plurality of monitors in the respective corresponding monitoring areas, preprocessing the monitoring image data, and storing the monitoring image data;
step S2, calling monitoring image data meeting the requirement of a preset monitoring area position and/or the requirement of preset monitoring time from the stored monitoring image data according to a data calling instruction from the cloud terminal;
step S3, determining whether the called monitoring image data has abnormal image, and performing a security alarm operation on the corresponding monitoring area according to the determination result.
The beneficial effects of the above technical scheme are: the distributed safety monitoring method based on the multi-node edge computing equipment is characterized in that monitoring image data generated by monitors arranged in different monitoring areas in a distributed mode are preprocessed and stored, and proper monitoring image data are called to be analyzed and processed according to the corresponding monitoring area position and/or monitoring time requirements, so that safety alarm operation is performed on the corresponding monitoring areas according to the condition that whether image pictures are abnormal or not in the monitoring image data, and thus comprehensive monitoring and efficient safety alarm on the different monitoring areas can be realized, and all the monitoring areas can be ensured to obtain timely and reliable safety monitoring.
Preferably, in step S1, acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas, preprocessing the monitoring image data, and storing the monitoring image data specifically includes:
step S101, instructing a plurality of monitors to scan and shoot in respective corresponding monitored areas, thereby obtaining panoramic monitoring image data of the monitored areas;
step S102, extracting a plurality of monitoring image frames from the panoramic monitoring image data according to a preset time interval, wherein the plurality of monitoring image frames cover the monitoring area together, and performing background noise removal processing, graying processing and image edge sharpening processing on the plurality of monitoring image frames so as to obtain a plurality of preprocessed monitoring image frames;
and step S103, storing a plurality of preprocessed monitoring image frames to a data center according to the shooting time axis of the monitor.
The beneficial effects of the above technical scheme are: the plurality of monitors are arranged in different monitoring areas in a distributed mode and respectively monitor the monitoring areas, and corresponding panoramic monitoring image data can be obtained by indicating the monitors to perform scanning shooting, so that the condition of monitoring area omission can be avoided; in addition, because of being limited by the actual monitoring environmental conditions of the monitor, the obtained panoramic monitoring image data inevitably has certain noise interference components, and the noise interference components in the panoramic monitoring image data can be effectively removed by extracting a plurality of monitoring image frames from the panoramic monitoring image data and carrying out background noise removal processing, graying processing and image edge sharpening processing, so that the storage effectiveness of the data center on the monitoring image data is improved.
Preferably, in step S2, according to the data retrieving instruction from the cloud terminal, retrieving the monitoring image data meeting the requirement of the preset monitoring area position and/or the requirement of the preset monitoring time from the stored monitoring image data specifically includes:
step S201, acquiring a data calling instruction from a cloud terminal, and analyzing the data calling instruction, so as to determine monitoring area position information and/or monitoring time information which needs to be subjected to data calling;
step S202, according to the position information and/or the monitoring time information of the monitoring area, searching and positioning from the data center to obtain monitoring image data matched with the position information and/or the monitoring time information of the monitoring area.
The beneficial effects of the above technical scheme are: when the monitoring image data is stored in the data center, the monitoring area position information and the monitoring time information corresponding to the monitoring image data are used as the accessory index information to be synchronously stored, so that after the data calling instruction is analyzed, the monitoring image data matched with the monitoring area position information and/or the monitoring time information can be accurately searched and positioned according to the calling requirement contained in the data calling instruction, and the calling speed and the accuracy of the monitoring image data are improved.
Preferably, in step S3, the determining whether the called monitoring image data has abnormal image picture, and performing the security alarm operation on the corresponding monitoring area according to the determination result specifically includes:
step S301, separating the taken monitoring image data to obtain a corresponding background picture and a character picture, and respectively extracting and processing image texture distribution information of the background picture and the character picture to obtain corresponding background picture texture distribution information and character picture texture distribution information;
step S302, according to the background picture texture distribution information and the figure picture texture distribution information, respectively determining a background picture texture change value corresponding to the background picture and a figure picture texture change value corresponding to the figure picture, and determining an absolute value of a difference value between the background picture texture change value and the figure picture texture change value;
step S303, comparing the absolute value of the difference with a preset difference threshold, if the absolute value of the difference is smaller than the preset difference threshold, determining that the called monitoring image data has no image frame abnormity, otherwise, determining that the called monitoring image data has the image frame abnormity;
step S304, carrying out safety alarm operation in a sound mode and/or a light mode on the monitored area corresponding to the monitored image data with the determined abnormal image picture.
The beneficial effects of the above technical scheme are: when the monitored area has potential safety hazard, the environment background and/or the person object corresponding to the monitored area will change, correspondingly, the image texture distribution states of the background picture and the person picture in the monitored image data corresponding to the monitored area will have difference of different degrees, and the existence of image picture abnormity in the called monitored image data can be quantitatively judged by judging the magnitude relation between the absolute value of the difference value between the background picture texture change value and the person picture texture change value and the preset difference threshold value, so that the convenience and reliability of judging whether the monitored area is normal or not are improved, and the safe alarm operation of sound mode and/or light mode can be conveniently carried out on the monitored area in follow-up time.
Preferably, in step S3, the determining whether the called monitoring image data has abnormal image picture, and performing the security alarm operation on the corresponding monitoring area according to the determination result specifically includes:
calling two target monitoring images within a preset interval duration, dividing each target monitoring image into a target number of regions with equal area size, and obtaining texture features in each region in each target monitoring image;
calculating the color recovery factor of each target monitoring image according to the texture features in each region in each target monitoring image by using the following formula (1),
in the above formula (1), C1A color recovery factor representing the 1 st target monitor image, N representing the number of divided regions, Si1Expressing the definition of textural features in the ith area of the 1 st target monitoring image, beta expressing a gain coefficient, log expressing a logarithm operation, theta expressing a preset external environment influence factor coefficient, Ii1Linear intensity, L, of textural features in the ith region of the 1 st target monitor imagei1I (th) representing 1 st target monitoring imageLength of the region, Li2Indicating the width of the ith area of the 1 st target monitoring image;
determining the current change degree of the 2 nd target monitoring image relative to the 1 st target monitoring image by using the following formula (2) and the color recovery factor of each target monitoring image,
in the above formula (2), b represents the current degree of change of the 2 nd target monitoring image relative to the 1 st target monitoring image, K represents a contrast factor, C2A color recovery factor representing the 2 nd target monitor image, A representing the number of feature points in the 2 nd target monitor image, Q2jRepresenting the size parameter of the jth characteristic point in the 2 nd target monitoring image, B representing the number of the characteristic points in the 1 st target monitoring image, D1uA size parameter T representing the u-th feature point in the 1 st target monitoring image2Indicates the photographing time length, T, of the 2 nd target monitoring image1The shooting time of the 1 st target monitoring image is represented, and the T represents the interval time between the 1 st target monitoring image and the 2 nd target monitoring image;
and determining whether the current change degree is within a preset change degree interval, if so, judging that the two target monitoring images have no image frame abnormity, otherwise, judging that the two target monitoring images have image frame abnormity, and sending an alarm prompt to a user.
The beneficial effects of the above technical scheme are: the influence of external interference factors on the calculation result can be eliminated by calculating the color recovery factor of each target monitoring image, the self parameters of the two target monitoring images can be displayed more obviously according to the color recovery factor, the interference of the illumination intensity of the external environment on the comparison is eliminated, furthermore, the characteristic points in the two target monitoring images can be used as comparison objects to compare the parameters by calculating the current change degree of the 2 nd target monitoring image relative to the 1 st target monitoring image, the change degrees of the two target monitoring images are determined without manual observation, the labor cost is saved, the interference of human subjective factors is eliminated, the final calculation result is more practical and accurate, the accuracy of data is ensured, the occurrence of false alarm conditions is avoided, and the overall stability and practicability are improved.
Fig. 2 is a schematic structural diagram of a distributed security monitoring system based on a multi-node edge computing device according to an embodiment of the present invention. The distributed safety monitoring system based on the multi-node edge computing equipment comprises a monitoring image data acquisition module, a monitoring image data preprocessing and storing module, a monitoring image data calling module and a monitoring area safety alarm module; wherein the content of the first and second substances,
the monitoring image data acquisition module is used for acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas;
the monitoring image data preprocessing and storing module is used for preprocessing the monitoring image data and then storing the monitoring image data;
the monitoring image data calling module is used for calling monitoring image data meeting the position requirement and/or the preset monitoring time requirement of a preset monitoring area from the stored monitoring image data according to a data calling instruction from the cloud terminal;
the monitoring area safety alarm module is used for judging whether the called monitoring image data has abnormal image pictures or not and carrying out safety alarm operation on the corresponding monitoring area according to the judgment result.
The beneficial effects of the above technical scheme are: the distributed safety monitoring system based on the multi-node edge computing equipment preprocesses and stores monitoring image data generated by monitors arranged in different monitoring areas in a distributed mode, calls appropriate monitoring image data according to corresponding monitoring area positions and/or monitoring time requirements and analyzes and processes the monitoring image data, and accordingly carries out safety alarm operation on the corresponding monitoring areas according to the condition that whether image pictures are abnormal or not in the monitoring image data, so that comprehensive monitoring and efficient safety alarm on the different monitoring areas can be achieved, and timely and reliable safety monitoring of all the monitoring areas can be guaranteed.
Preferably, the acquiring of the monitoring image data by the monitoring image data acquiring module includes:
instructing a plurality of monitors to carry out scanning shooting in respective corresponding monitored areas so as to obtain panoramic monitoring image data about the monitored areas;
and the number of the first and second groups,
after the monitoring image data is preprocessed by the monitoring image data preprocessing and storing module, the storing of the monitoring image data specifically comprises the following steps:
extracting a plurality of monitoring image frames from the panoramic monitoring image data according to a preset time interval, wherein the plurality of monitoring image frames cover the monitoring area together, and performing background noise removal processing, graying processing and image edge sharpening processing on the plurality of monitoring image frames so as to obtain a plurality of preprocessed monitoring image frames;
and then storing a plurality of the preprocessed monitoring image frames to a data center according to the shooting time axis of the monitor.
The beneficial effects of the above technical scheme are: the plurality of monitors are arranged in different monitoring areas in a distributed mode and respectively monitor the monitoring areas, and corresponding panoramic monitoring image data can be obtained by indicating the monitors to perform scanning shooting, so that the condition of monitoring area omission can be avoided; in addition, because of being limited by the actual monitoring environmental conditions of the monitor, the obtained panoramic monitoring image data inevitably has certain noise interference components, and the noise interference components in the panoramic monitoring image data can be effectively removed by extracting a plurality of monitoring image frames from the panoramic monitoring image data and carrying out background noise removal processing, graying processing and image edge sharpening processing, so that the storage effectiveness of the data center on the monitoring image data is improved.
Preferably, the retrieving of the monitoring image data, which meets the requirement of a preset monitoring area and/or the requirement of preset monitoring time, from the stored monitoring image data according to the data retrieving instruction from the cloud terminal by the monitoring image data retrieving module specifically includes:
acquiring a data calling instruction from a cloud terminal, and analyzing the data calling instruction so as to determine monitoring area position information and/or monitoring time information which needs to be subjected to data calling;
and searching and positioning from the data center according to the position information and/or the monitoring time information of the monitoring area to obtain monitoring image data matched with the position information and/or the monitoring time information of the monitoring area.
The beneficial effects of the above technical scheme are: when the monitoring image data is stored in the data center, the monitoring area position information and the monitoring time information corresponding to the monitoring image data are used as the accessory index information to be synchronously stored, so that after the data calling instruction is analyzed, the monitoring image data matched with the monitoring area position information and/or the monitoring time information can be accurately searched and positioned according to the calling requirement contained in the data calling instruction, and the calling speed and the accuracy of the monitoring image data are improved.
Preferably, the monitoring area security alarm module judges whether the called monitoring image data has an abnormal image picture condition, and according to the judgment result, the security alarm operation for the corresponding monitoring area specifically includes:
separating the called monitoring image data to obtain a corresponding background picture and a character picture, and respectively extracting and processing image texture distribution information of the background picture and the character picture so as to obtain corresponding background picture texture distribution information and character picture texture distribution information;
respectively determining a background picture texture change value corresponding to the background picture and a figure picture texture change value corresponding to the figure picture according to the background picture texture distribution information and the figure picture texture distribution information, and determining an absolute value of a difference value between the background picture texture change value and the figure picture texture change value;
comparing the absolute value of the difference with a preset difference threshold, if the absolute value of the difference is smaller than the preset difference threshold, determining that the condition of image frame abnormality does not exist in the called monitoring image data, otherwise, determining that the condition of image frame abnormality exists in the called monitoring image data;
and carrying out safety alarm operation in a sound mode and/or a light mode on a monitoring area corresponding to the monitoring image data with the determined image picture abnormity.
The beneficial effects of the above technical scheme are: when the monitored area has potential safety hazard, the environment background and/or the person object corresponding to the monitored area will change, correspondingly, the image texture distribution states of the background picture and the person picture in the monitored image data corresponding to the monitored area will have difference of different degrees, and the existence of image picture abnormity in the called monitored image data can be quantitatively judged by judging the magnitude relation between the absolute value of the difference value between the background picture texture change value and the person picture texture change value and the preset difference threshold value, so that the convenience and reliability of judging whether the monitored area is normal or not are improved, and the safe alarm operation of sound mode and/or light mode can be conveniently carried out on the monitored area in follow-up time.
As can be seen from the content of the above embodiment, the distributed security monitoring method and system based on the multi-node edge computing device obtain the monitoring image data generated by the plurality of monitors in the respective corresponding monitoring areas, preprocess the monitoring image data, store the monitoring image data, call the monitoring image data meeting the requirements of the preset monitoring area position and/or the preset monitoring time from the stored monitoring image data according to the data call instruction from the cloud terminal, determine whether the called monitoring image data has the abnormal image picture condition, and perform the security alarm operation on the corresponding monitoring area according to the determination result; therefore, the distributed safety monitoring method and the system based on the multi-node edge computing equipment preprocess and store the monitoring image data generated by the monitors arranged in different monitoring areas in a distributed mode, and call appropriate monitoring image data for analysis and processing according to the corresponding monitoring area position and/or monitoring time requirements, so that the corresponding monitoring areas are subjected to safety alarm operation according to the condition whether image picture abnormity exists in the monitoring image data, thus realizing comprehensive monitoring and efficient safety alarm of the different monitoring areas and ensuring that all monitoring areas can obtain timely and reliable safety monitoring.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. The distributed security monitoring method based on the multi-node edge computing equipment is characterized by comprising the following steps of:
step S1, acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas, preprocessing the monitoring image data, and storing the monitoring image data;
step S2, calling monitoring image data meeting the requirement of a preset monitoring area position and/or the requirement of preset monitoring time from the stored monitoring image data according to a data calling instruction from the cloud terminal;
and step S3, judging whether the called monitoring image data has abnormal image picture condition, and carrying out safety alarm operation on the corresponding monitoring area according to the judgment result.
2. The distributed security monitoring method based on multi-node edge computing devices of claim 1, wherein:
in step S1, acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas, preprocessing the monitoring image data, and storing the monitoring image data specifically includes:
step S101, instructing a plurality of monitors to scan and shoot in respective corresponding monitored areas so as to obtain panoramic monitoring image data of the monitored areas;
step S102, extracting a plurality of monitoring image frames from the panoramic monitoring image data according to a preset time interval, wherein the plurality of monitoring image frames cover the monitoring area together, and performing background noise removal processing, graying processing and image edge sharpening processing on the plurality of monitoring image frames so as to obtain a plurality of preprocessed monitoring image frames;
and step S103, storing a plurality of preprocessed monitoring image frames to a data center according to the shooting time axis of the monitor.
3. The distributed security monitoring method based on multi-node edge computing devices of claim 2, wherein:
in step S2, according to a data retrieval instruction from a cloud terminal, retrieving, from the stored monitoring image data, monitoring image data that meets a preset monitoring area position requirement and/or a preset monitoring time requirement specifically includes:
step S201, acquiring a data calling instruction from a cloud terminal, and analyzing the data calling instruction so as to determine monitoring area position information and/or monitoring time information which needs to be subjected to data calling;
step S202, according to the monitoring area position information and/or the monitoring time information, searching and positioning from the data center to obtain monitoring image data matched with the monitoring area position information and/or the monitoring time information.
4. The multi-node edge computing device based distributed security monitoring method and system of claim 3, wherein:
in step S3, determining whether the called monitoring image data has an abnormal image, and performing a security alarm operation on the corresponding monitoring area according to the determination result specifically includes:
step S301, separating the taken monitoring image data to obtain a corresponding background picture and a character picture, and respectively extracting and processing image texture distribution information of the background picture and the character picture to obtain corresponding background picture texture distribution information and character picture texture distribution information;
step S302, according to the background picture texture distribution information and the figure picture texture distribution information, respectively determining a background picture texture change value corresponding to the background picture and a figure picture texture change value corresponding to the figure picture, and determining an absolute value of a difference value between the background picture texture change value and the figure picture texture change value;
step S303, comparing the absolute value of the difference with a preset difference threshold, if the absolute value of the difference is smaller than the preset difference threshold, determining that the called monitoring image data has no image frame abnormity, otherwise, determining that the called monitoring image data has the image frame abnormity;
step S304, carrying out safety alarm operation in a sound mode and/or a light mode on the monitored area corresponding to the monitored image data with the determined abnormal image picture.
5. The multi-node edge computing device based distributed security monitoring method and system of claim 2, wherein:
in step S3, determining whether the called monitoring image data has an abnormal image, and performing a security alarm operation on the corresponding monitoring area according to the determination result specifically includes:
calling two target monitoring images within a preset interval duration, dividing each target monitoring image into a target number of regions with equal area size, and obtaining texture features in each region in each target monitoring image;
calculating the color recovery factor of each target monitoring image according to the texture features in each region in each target monitoring image by using the following formula (1),
in the above formula (1), C1A color recovery factor representing the 1 st target monitor image, N representing the number of divided regions, Si1Expressing the definition of textural features in the ith area of the 1 st target monitoring image, beta expressing a gain coefficient, log expressing a logarithm operation, theta expressing a preset external environment influence factor coefficient, Ii1Linear intensity, L, of textural features in the ith region of the 1 st target monitor imagei1Length, L, of the i-th area representing the 1 st target monitoring imagei2Indicating the width of the ith area of the 1 st target monitoring image;
determining the current change degree of the 2 nd target monitoring image relative to the 1 st target monitoring image by using the following formula (2) and the color recovery factor of each target monitoring image,
in the above formula (2), b represents the current degree of change of the 2 nd target monitoring image relative to the 1 st target monitoring image, K represents a contrast factor, C2A color recovery factor representing the 2 nd target monitor image, A representing the number of feature points in the 2 nd target monitor image, Q2jRepresenting the size parameter of the jth characteristic point in the 2 nd target monitoring image, B representing the number of the characteristic points in the 1 st target monitoring image, D1uA size parameter T representing the u-th feature point in the 1 st target monitoring image2Indicates the photographing time length, T, of the 2 nd target monitoring image1The shooting time of the 1 st target monitoring image is represented, and the T represents the interval time between the 1 st target monitoring image and the 2 nd target monitoring image;
and confirming whether the current change degree is within a preset change degree interval, if so, judging that the two target monitoring images have no abnormal image picture condition, otherwise, judging that the two target monitoring images have the abnormal image picture condition, and sending an alarm prompt to a user.
6. The distributed safety monitoring system based on the multi-node edge computing equipment is characterized by comprising a monitoring image data acquisition module, a monitoring image data preprocessing and storing module, a monitoring image data calling module and a monitoring area safety alarm module; wherein the content of the first and second substances,
the monitoring image data acquisition module is used for acquiring monitoring image data generated by a plurality of monitors in respective corresponding monitoring areas;
the monitoring image data preprocessing and storing module is used for preprocessing the monitoring image data and then storing the monitoring image data;
the monitoring image data calling module is used for calling monitoring image data meeting the position requirement and/or the preset monitoring time requirement of a preset monitoring area from the stored monitoring image data according to a data calling instruction from a cloud terminal;
the monitoring area safety alarm module is used for judging whether the called monitoring image data has abnormal image pictures or not and carrying out safety alarm operation on the corresponding monitoring area according to the judgment result.
7. The distributed security monitoring system based on multi-node edge computing devices of claim 5, wherein:
the acquiring of the monitoring image data generated by the plurality of monitors in the respective corresponding monitoring areas by the monitoring image data acquiring module specifically includes:
instructing a plurality of monitors to carry out scanning shooting in respective corresponding monitored areas so as to obtain panoramic monitoring image data about the monitored areas;
and the number of the first and second groups,
after the monitoring image data preprocessing and storing module preprocesses the monitoring image data, storing the monitoring image data specifically comprises:
extracting a plurality of monitoring image frames from the panoramic monitoring image data according to a preset time interval, wherein the plurality of monitoring image frames cover the monitoring area together, and performing background noise removal processing, graying processing and image edge sharpening processing on the plurality of monitoring image frames so as to obtain a plurality of preprocessed monitoring image frames;
and storing a plurality of preprocessed monitoring image frames to a data center according to the shooting time axis of the monitor.
8. The distributed security monitoring system based on multi-node edge computing devices of claim 6, wherein:
the monitoring image data calling module calls monitoring image data meeting the preset monitoring area position requirement and/or the preset monitoring time requirement from the stored monitoring image data according to a data calling instruction from a cloud terminal, and the monitoring image data calling module specifically comprises the following steps:
acquiring a data calling instruction from a cloud terminal, and analyzing the data calling instruction so as to determine monitoring area position information and/or monitoring time information which needs to be subjected to data calling;
and searching and positioning from the data center according to the position information and/or the monitoring time information of the monitoring area to obtain monitoring image data matched with the position information and/or the monitoring time information of the monitoring area.
9. The distributed security monitoring system based on multi-node edge computing devices of claim 7, wherein:
the monitoring area safety alarm module judges whether the called monitoring image data has the condition of abnormal image picture, and according to the judgment result, the safety alarm operation of the corresponding monitoring area specifically comprises the following steps:
separating the called monitoring image data to obtain a corresponding background picture and a character picture, and respectively extracting and processing image texture distribution information of the background picture and the character picture so as to obtain corresponding background picture texture distribution information and character picture texture distribution information;
respectively determining a background picture texture change value corresponding to the background picture and a figure picture texture change value corresponding to the figure picture according to the background picture texture distribution information and the figure picture texture distribution information, and determining an absolute value of a difference value between the background picture texture change value and the figure picture texture change value;
comparing the absolute value of the difference with a preset difference threshold, if the absolute value of the difference is smaller than the preset difference threshold, determining that the condition of image frame abnormality does not exist in the called monitoring image data, otherwise, determining that the condition of image frame abnormality exists in the called monitoring image data; and carrying out safety alarm operation in a sound mode and/or a light mode on a monitoring area corresponding to the monitoring image data with the determined image picture abnormity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011545945.3A CN112637568B (en) | 2020-12-24 | 2020-12-24 | Distributed security monitoring method and system based on multi-node edge computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011545945.3A CN112637568B (en) | 2020-12-24 | 2020-12-24 | Distributed security monitoring method and system based on multi-node edge computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112637568A true CN112637568A (en) | 2021-04-09 |
| CN112637568B CN112637568B (en) | 2021-11-23 |
Family
ID=75324197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011545945.3A Active CN112637568B (en) | 2020-12-24 | 2020-12-24 | Distributed security monitoring method and system based on multi-node edge computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112637568B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658229A (en) * | 2021-08-13 | 2021-11-16 | 杭州华橙软件技术有限公司 | Abnormal object determination method and device, storage medium and electronic device |
| CN114969167A (en) * | 2022-04-07 | 2022-08-30 | 江苏尚蓝信息技术有限公司 | Intelligent power grid monitoring comprehensive management system and method based on digitization |
| CN116939171A (en) * | 2023-09-19 | 2023-10-24 | 南方电网数字电网研究院有限公司 | Power transmission line monitoring method, device and computer equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060195199A1 (en) * | 2003-10-21 | 2006-08-31 | Masahiro Iwasaki | Monitoring device |
| CN101489022A (en) * | 2008-01-16 | 2009-07-22 | 延世大学工业学术合作社 | Color recovery method and system |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| US20100253779A1 (en) * | 2009-03-02 | 2010-10-07 | Masaya Itoh | Video image monitoring system |
| CN101916448A (en) * | 2010-08-09 | 2010-12-15 | 云南清眸科技有限公司 | Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern) |
| US20110304467A1 (en) * | 2010-06-14 | 2011-12-15 | Hon Hai Precision Industry Co., Ltd. | Image monitoring device and method |
| CN104077872A (en) * | 2014-05-13 | 2014-10-01 | 国家电网公司 | Anti-external force monitoring early warning method of electric transmission line based on image recognition |
| CN108040220A (en) * | 2017-11-16 | 2018-05-15 | 杭州好园科技有限公司 | Wisdom garden video monitoring system |
| CN108091160A (en) * | 2017-11-16 | 2018-05-29 | 杭州好园科技有限公司 | The induction in wisdom garden parking lot and seek vehicle system |
| US20180300124A1 (en) * | 2015-08-27 | 2018-10-18 | FogHorn Systems, Inc. | Edge Computing Platform |
| CN109672750A (en) * | 2019-01-15 | 2019-04-23 | 特斯联（北京）科技有限公司 | A kind of security protection data aggregate management system and its management method based on Edge fabrics |
| CN109902640A (en) * | 2019-03-05 | 2019-06-18 | 江南大学 | Video quality abnormality detection system and its detection method based on edge calculations and machine learning |
| CN110532857A (en) * | 2019-07-16 | 2019-12-03 | 杭州电子科技大学 | Based on the Activity recognition image analysis system under multi-cam |
| CN111898486A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Method and device for detecting abnormity of monitoring picture and storage medium |
-
2020
- 2020-12-24 CN CN202011545945.3A patent/CN112637568B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060195199A1 (en) * | 2003-10-21 | 2006-08-31 | Masahiro Iwasaki | Monitoring device |
| CN101489022A (en) * | 2008-01-16 | 2009-07-22 | 延世大学工业学术合作社 | Color recovery method and system |
| US20100253779A1 (en) * | 2009-03-02 | 2010-10-07 | Masaya Itoh | Video image monitoring system |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| US20110304467A1 (en) * | 2010-06-14 | 2011-12-15 | Hon Hai Precision Industry Co., Ltd. | Image monitoring device and method |
| CN101916448A (en) * | 2010-08-09 | 2010-12-15 | 云南清眸科技有限公司 | Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern) |
| CN104077872A (en) * | 2014-05-13 | 2014-10-01 | 国家电网公司 | Anti-external force monitoring early warning method of electric transmission line based on image recognition |
| US20180300124A1 (en) * | 2015-08-27 | 2018-10-18 | FogHorn Systems, Inc. | Edge Computing Platform |
| CN108040220A (en) * | 2017-11-16 | 2018-05-15 | 杭州好园科技有限公司 | Wisdom garden video monitoring system |
| CN108091160A (en) * | 2017-11-16 | 2018-05-29 | 杭州好园科技有限公司 | The induction in wisdom garden parking lot and seek vehicle system |
| CN109672750A (en) * | 2019-01-15 | 2019-04-23 | 特斯联（北京）科技有限公司 | A kind of security protection data aggregate management system and its management method based on Edge fabrics |
| CN109902640A (en) * | 2019-03-05 | 2019-06-18 | 江南大学 | Video quality abnormality detection system and its detection method based on edge calculations and machine learning |
| CN110532857A (en) * | 2019-07-16 | 2019-12-03 | 杭州电子科技大学 | Based on the Activity recognition image analysis system under multi-cam |
| CN111898486A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Method and device for detecting abnormity of monitoring picture and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658229A (en) * | 2021-08-13 | 2021-11-16 | 杭州华橙软件技术有限公司 | Abnormal object determination method and device, storage medium and electronic device |
| CN113658229B (en) * | 2021-08-13 | 2024-02-02 | 杭州华橙软件技术有限公司 | Method and device for determining abnormal object, storage medium and electronic device |
| CN114969167A (en) * | 2022-04-07 | 2022-08-30 | 江苏尚蓝信息技术有限公司 | Intelligent power grid monitoring comprehensive management system and method based on digitization |
| CN114969167B (en) * | 2022-04-07 | 2024-02-06 | 江苏尚蓝信息技术有限公司 | Intelligent power grid monitoring integrated management system and method based on data |
| CN116939171A (en) * | 2023-09-19 | 2023-10-24 | 南方电网数字电网研究院有限公司 | Power transmission line monitoring method, device and computer equipment |
| CN116939171B (en) * | 2023-09-19 | 2024-03-26 | 南方电网数字电网研究院有限公司 | Power transmission line monitoring method, device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112637568B (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112637568B (en) | Distributed security monitoring method and system based on multi-node edge computing equipment | |
| CN110705405B (en) | Target labeling method and device | |
| CN110781839A (en) | Sliding window-based small and medium target identification method in large-size image | |
| CN112200011B (en) | Aeration tank state detection method, system, electronic equipment and storage medium | |
| CN111160202A (en) | AR equipment-based identity verification method, AR equipment-based identity verification device, AR equipment-based identity verification equipment and storage medium | |
| CN111898486A (en) | Method and device for detecting abnormity of monitoring picture and storage medium | |
| CN109508636A (en) | Vehicle attribute recognition methods, device, storage medium and electronic equipment | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN113822385B (en) | Coal conveying abnormity monitoring method, device and equipment based on image and storage medium | |
| CN111597889A (en) | Method, device and system for detecting target movement in video | |
| CN116503807A (en) | Equipment inspection method, device, electronic equipment and computer program product | |
| CN113158773B (en) | Training method and training device for living body detection model | |
| CN115690747A (en) | Vehicle blind area detection model test method and device, electronic equipment and storage medium | |
| CN112073713B (en) | Video leakage test method, device, equipment and storage medium | |
| CN111127701B (en) | Vehicle failure scene detection method and system | |
| CN115311680A (en) | Human body image quality detection method and device, electronic equipment and storage medium | |
| CN111669575B (en) | Method, system, electronic device, medium and terminal for testing image processing effect | |
| CN115131725A (en) | Traffic flow statistical method, device, equipment and storage medium | |
| CN114758384A (en) | Face detection method, device, equipment and storage medium | |
| CN114565870A (en) | Production line control method, device and system based on vision, and electronic equipment | |
| CN114529497A (en) | Method, system, storage medium, and computer device for detecting aged screen | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN113111777A (en) | Indoor personnel density detection system and detection method based on ARM platform | |
| CN114463242A (en) | Image detection method, device, storage medium and device | |
| CN115019055A (en) | Image matching method and device, intelligent equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |